Visual Analytics on Network Forgetting for Task‐Incremental Learning

Task‐incremental learning (Task‐IL) aims to enable an intelligent agent to continuously accumulate knowledge from new learning tasks without catastrophically forgetting what it has learned in the past. It has drawn increasing attention in recent years, with many algorithms being proposed to mitigate...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer graphics forum Jg. 42; H. 3; S. 437 - 448
Hauptverfasser: Li, Ziwei, Xu, Jiayi, Chao, Wei‐Lun, Shen, Han‐Wei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Oxford Blackwell Publishing Ltd 01.06.2023
Schlagworte:
ISSN:0167-7055, 1467-8659
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Task‐incremental learning (Task‐IL) aims to enable an intelligent agent to continuously accumulate knowledge from new learning tasks without catastrophically forgetting what it has learned in the past. It has drawn increasing attention in recent years, with many algorithms being proposed to mitigate neural network forgetting. However, none of the existing strategies is able to completely eliminate the issues. Moreover, explaining and fully understanding what knowledge and how it is being forgotten during the incremental learning process still remains under‐explored. In this paper, we propose KnowledgeDrift, a visual analytics framework, to interpret the network forgetting with three objectives: (1) to identify when the network fails to memorize the past knowledge, (2) to visualize what information has been forgotten, and (3) to diagnose how knowledge attained in the new model interferes with the one learned in the past. Our analytical framework first identifies the occurrence of forgetting by tracking the task performance under the incremental learning process and then provides in‐depth inspections of drifted information via various levels of data granularity. KnowledgeDrift allows analysts and model developers to enhance their understanding of network forgetting and compare the performance of different incremental learning algorithms. Three case studies are conducted in the paper to further provide insights and guidance for users to effectively diagnose catastrophic forgetting over time.
AbstractList Task‐incremental learning (Task‐IL) aims to enable an intelligent agent to continuously accumulate knowledge from new learning tasks without catastrophically forgetting what it has learned in the past. It has drawn increasing attention in recent years, with many algorithms being proposed to mitigate neural network forgetting. However, none of the existing strategies is able to completely eliminate the issues. Moreover, explaining and fully understanding what knowledge and how it is being forgotten during the incremental learning process still remains under‐explored. In this paper, we propose KnowledgeDrift, a visual analytics framework, to interpret the network forgetting with three objectives: (1) to identify when the network fails to memorize the past knowledge, (2) to visualize what information has been forgotten, and (3) to diagnose how knowledge attained in the new model interferes with the one learned in the past. Our analytical framework first identifies the occurrence of forgetting by tracking the task performance under the incremental learning process and then provides in‐depth inspections of drifted information via various levels of data granularity. KnowledgeDrift allows analysts and model developers to enhance their understanding of network forgetting and compare the performance of different incremental learning algorithms. Three case studies are conducted in the paper to further provide insights and guidance for users to effectively diagnose catastrophic forgetting over time.
Author Chao, Wei‐Lun
Xu, Jiayi
Li, Ziwei
Shen, Han‐Wei
Author_xml – sequence: 1
  givenname: Ziwei
  surname: Li
  fullname: Li, Ziwei
  organization: The Ohio State University
– sequence: 2
  givenname: Jiayi
  surname: Xu
  fullname: Xu, Jiayi
  organization: The Ohio State University
– sequence: 3
  givenname: Wei‐Lun
  surname: Chao
  fullname: Chao, Wei‐Lun
  organization: The Ohio State University
– sequence: 4
  givenname: Han‐Wei
  surname: Shen
  fullname: Shen, Han‐Wei
  organization: The Ohio State University
BookMark eNp9kM9OAjEQxhuDiYAefINNPHlY6L8t7ZEQF0mIXtBrU2qXFJYW2xLCzUfwGX0Sq3gy0bnMJPP7vsx8PdBx3hkArhEcoFxDvWoGiHKKz0AXUTYqOatEB3QhyvMIVtUF6MW4hhDSEau6oH62ca_aYuxUe0xWx8K74sGkgw-bovZhZVKyblU0PhQLFTcfb-8zp4PZGpeybG5UcHl_Cc4b1UZz9dP74Km-W0zuy_njdDYZz0tNCMYlQ0uNKoE0bCqiORGEG0x4QwVZCiE4JkYQLBStECGMaUbyC41Y6hdmCNOU9MHNyXcX_OvexCTXfh_y7VFijgWHGHKeqdsTpYOPMZhG7oLdqnCUCMqvmGSOSX7HlNnhL1bbpJL1LgVl2_8UB9ua49_WcjKtT4pPmmt6EA
CitedBy_id crossref_primary_10_1109_MCG_2024_3360881
Cites_doi 10.32614/CRAN.package.uwot
10.1073/pnas.1611835114
10.1080/095400900116177
10.1016/j.neunet.2019.01.012
10.1109/TVCG.2020.2973258
10.1007/s11263-015-0816-y
10.1109/CVPR.2016.90
10.1109/VIS47514.2020.00065
10.1145/2702123.2702509
10.1109/VAST.2018.8802509
10.1609/aaai.v34i09.7079
10.1109/TVCG.2016.2598838
10.1109/TPAMI.2017.2773081
10.1145/3027063.3053103
10.1007/978-1-4615-5529-2_11
10.1007/978-3-030-01252-6_33
10.1609/aaai.v32i1.11595
10.1109/TVCG.2022.3209347
10.3389/fpsyg.2013.00504
10.1109/ICCV.2019.00653
10.1016/S0764-4469(97)82472-9
10.1109/ICCV.2017.322
10.1109/TVCG.2020.3030461
10.1109/TVCG.2018.2864504
ContentType Journal Article
Copyright 2023 The Authors. Computer Graphics Forum published by Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
2023. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2023 The Authors. Computer Graphics Forum published by Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
– notice: 2023. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 24P
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1111/cgf.14842
DatabaseName Wiley Online Library Open Access (WRLC)
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts

CrossRef
Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access (WRLC)
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1467-8659
EndPage 448
ExternalDocumentID 10_1111_cgf_14842
CGF14842
Genre article
GrantInformation_xml – fundername: NSF‐funded AI institute
  funderid: OAC‐2112606
GroupedDBID .3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
15B
1OB
1OC
24P
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8VB
930
A03
AAESR
AAEVG
AAHHS
AAHQN
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABDPE
ABEML
ABPVW
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
ADZOD
AEEZP
AEGXH
AEIGN
AEIMD
AEMOZ
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFPWT
AFWVQ
AFZJQ
AHBTC
AHEFC
AHQJS
AITYG
AIURR
AIWBW
AJBDE
AJXKR
AKVCP
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EAD
EAP
EBA
EBO
EBR
EBS
EBU
EDO
EJD
EMK
EST
ESX
F00
F01
F04
F5P
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K1G
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QWB
R.K
RDJ
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
TH9
TN5
TUS
UB1
V8K
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WRC
WXSBR
WYISQ
WZISG
XG1
ZL0
ZZTAW
~IA
~IF
~WT
AAMMB
AAYXX
ADMLS
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c3322-61bc1591c0f53c83938e238f493b999823e9329a4513366c63467f9bcd6e36c43
IEDL.DBID DRFUL
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001020716600036&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-7055
IngestDate Fri Jul 25 04:29:28 EDT 2025
Sat Nov 29 03:41:22 EST 2025
Tue Nov 18 22:28:53 EST 2025
Wed Jan 22 16:22:00 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
License Attribution
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3322-61bc1591c0f53c83938e238f493b999823e9329a4513366c63467f9bcd6e36c43
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.14842
PQID 2829802088
PQPubID 30877
PageCount 12
ParticipantIDs proquest_journals_2829802088
crossref_primary_10_1111_cgf_14842
crossref_citationtrail_10_1111_cgf_14842
wiley_primary_10_1111_cgf_14842_CGF14842
PublicationCentury 2000
PublicationDate June 2023
2023-06-00
20230601
PublicationDateYYYYMMDD 2023-06-01
PublicationDate_xml – month: 06
  year: 2023
  text: June 2023
PublicationDecade 2020
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Computer graphics forum
PublicationYear 2023
Publisher Blackwell Publishing Ltd
Publisher_xml – name: Blackwell Publishing Ltd
References 2017; 40
2013; 4
2021; 44
1998
2020; 34
2017; 114
2018; 25
2021; 34
2015; 115
2022
1986; 86
2000; 12
2021
2020
1997; 320
2019
2020; 27
2018
2019; 113
2017
2016
2015
2014
2013
2018; 31
2016; 23
e_1_2_10_23_2
e_1_2_10_21_2
e_1_2_10_42_2
e_1_2_10_40_2
De Lange M. (e_1_2_10_12_2) 2021; 44
e_1_2_10_2_2
e_1_2_10_18_2
e_1_2_10_39_2
e_1_2_10_53_2
e_1_2_10_4_2
e_1_2_10_16_2
e_1_2_10_6_2
e_1_2_10_14_2
e_1_2_10_35_2
e_1_2_10_11_2
e_1_2_10_34_2
e_1_2_10_8_2
Zeiler M. D. (e_1_2_10_54_2) 2014
Yin H. (e_1_2_10_52_2) 2021; 34
e_1_2_10_51_2
Kornblith S. (e_1_2_10_22_2) 2019
e_1_2_10_29_2
e_1_2_10_27_2
e_1_2_10_48_2
e_1_2_10_25_2
e_1_2_10_46_2
e_1_2_10_45_2
e_1_2_10_20_2
e_1_2_10_43_2
e_1_2_10_41_2
Li H. (e_1_2_10_30_2) 2018; 31
e_1_2_10_19_2
Norton A. P. (e_1_2_10_37_2) 2017
e_1_2_10_3_2
e_1_2_10_17_2
e_1_2_10_5_2
e_1_2_10_15_2
e_1_2_10_38_2
Zenke F. (e_1_2_10_55_2) 2017
e_1_2_10_7_2
e_1_2_10_13_2
e_1_2_10_36_2
e_1_2_10_9_2
e_1_2_10_33_2
e_1_2_10_10_2
e_1_2_10_31_2
e_1_2_10_50_2
Schlimmer J. C. (e_1_2_10_44_2) 1986; 86
Mirzadeh S. I. (e_1_2_10_32_2) 2022
e_1_2_10_28_2
e_1_2_10_26_2
e_1_2_10_49_2
e_1_2_10_24_2
e_1_2_10_47_2
References_xml – volume: 12
  start-page: 1
  issue: 1
  year: 2000
  end-page: 19
  article-title: Neural networks with a self-refreshing memory: knowledge transfer in sequential learning tasks without catastrophic forgetting
  publication-title: Connection science
– start-page: 2961
  year: 2017
  end-page: 2969
– volume: 25
  start-page: 288
  issue: 1
  year: 2018
  end-page: 298
  article-title: Dqnviz: A visual analytics approach to understand deep q-networks
  publication-title: IEEE transactions on visualization and computer graphics
– volume: 113
  start-page: 54
  year: 2019
  end-page: 71
  article-title: Continual lifelong learning with neural networks: A review
  publication-title: Neural Networks
– start-page: 770
  year: 2016
  end-page: 778
– start-page: 261
  year: 1998
  end-page: 292
  article-title: Child: A first step towards continual learning
– year: 2021
– volume: 34
  start-page: 13544
  year: 2020
  end-page: 13549
  article-title: Learning on the job: Online lifelong and continual learning
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: 31
  year: 2018
  article-title: Visualizing the loss landscape of neural nets
  publication-title: Advances in neural information processing systems
– volume: 115
  start-page: 211
  issue: 3
  year: 2015
  end-page: 252
  article-title: Imagenet large scale visual recognition challenge
  publication-title: International journal of computer vision
– year: 2016
– year: 2018
– year: 2014
– start-page: 60
  year: 2018
  end-page: 71
  article-title: Analyzing the noise robustness of deep neural networks
– start-page: 1
  year: 2017
  end-page: 4
  article-title: Adversarial-playground: A visualization suite showing how adversarial examples fool deep learning
– start-page: 3987
  year: 2017
  end-page: 3995
  article-title: Continual learning through synaptic intelligence
– start-page: 818
  year: 2014
  end-page: 833
  article-title: Visualizing and understanding convolutional networks
– start-page: 532
  year: 2018
  end-page: 547
– volume: 27
  start-page: 3335
  issue: 7
  year: 2020
  end-page: 3349
  article-title: Oodanalyzer: Interactive analysis of out-of-distribution samples
  publication-title: IEEE transactions on visualization and computer graphics
– start-page: 3519
  year: 2019
  end-page: 3529
  article-title: Similarity of neural network representations revisited
– start-page: 1694
  year: 2017
  end-page: 1699
– year: 2022
– year: 2020
– volume: 23
  start-page: 101
  issue: 1
  year: 2016
  end-page: 110
  article-title: Visualizing the hidden activity of artificial neural networks
  publication-title: IEEE transactions on visualization and computer graphics
– volume: 86
  start-page: 496
  year: 1986
  end-page: 501
  article-title: A case study of incremental concept induction
  publication-title: AAAI
– volume: 320
  start-page: 989
  issue: 12
  year: 1997
  end-page: 997
  article-title: Avoiding catastrophic forgetting by coupling two reverberating neural networks
  publication-title: Comptes Rendus de l'Académie des Sciences-Series III-Sciences de la Vie
– start-page: 6430
  year: 2019
  end-page: 6439
– volume: 4
  start-page: 504
  year: 2013
  article-title: The stability-plasticity dilemma: Investigating the continuum from catastrophic forgetting to age-limited learning effects
  publication-title: Frontiers in psychology
– volume: 27
  start-page: 1364
  issue: 2
  year: 2020
  end-page: 1373
  article-title: Cnnpruner: Pruning convolutional neural networks with visual analytics
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– year: 2017
– volume: 34
  start-page: 10260
  year: 2021
  end-page: 10272
  article-title: Mitigating forgetting in online continual learning with neuron calibration
  publication-title: Advances in Neural Information Processing Systems
– volume: 114
  start-page: 3521
  issue: 13
  year: 2017
  end-page: 3526
  article-title: Overcoming catastrophic forgetting in neural networks
  publication-title: Proceedings of the national academy of sciences
– start-page: 15699
  year: 2022
  end-page: 15717
  article-title: Wide neural networks forget less catastrophically
– year: 2019
– volume: 44
  start-page: 3366
  issue: 7
  year: 2021
  end-page: 3385
  article-title: A continual learning survey: Defying forgetting in classification tasks
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– year: 2015
– volume: 40
  start-page: 2935
  issue: 12
  year: 2017
  end-page: 2947
  article-title: Learning without forgetting
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– year: 2013
– ident: e_1_2_10_34_2
– ident: e_1_2_10_26_2
– ident: e_1_2_10_35_2
  doi: 10.32614/CRAN.package.uwot
– start-page: 818
  volume-title: European conference on computer vision
  year: 2014
  ident: e_1_2_10_54_2
– ident: e_1_2_10_9_2
– ident: e_1_2_10_18_2
– ident: e_1_2_10_23_2
  doi: 10.1073/pnas.1611835114
– ident: e_1_2_10_11_2
– ident: e_1_2_10_5_2
  doi: 10.1080/095400900116177
– ident: e_1_2_10_17_2
– ident: e_1_2_10_39_2
  doi: 10.1016/j.neunet.2019.01.012
– ident: e_1_2_10_10_2
  doi: 10.1109/TVCG.2020.2973258
– ident: e_1_2_10_40_2
  doi: 10.1007/s11263-015-0816-y
– volume: 34
  start-page: 10260
  year: 2021
  ident: e_1_2_10_52_2
  article-title: Mitigating forgetting in online continual learning with neuron calibration
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_10_48_2
– ident: e_1_2_10_19_2
  doi: 10.1109/CVPR.2016.90
– ident: e_1_2_10_47_2
– ident: e_1_2_10_38_2
  doi: 10.1109/VIS47514.2020.00065
– ident: e_1_2_10_36_2
– ident: e_1_2_10_2_2
  doi: 10.1145/2702123.2702509
– ident: e_1_2_10_33_2
– ident: e_1_2_10_28_2
– start-page: 1
  volume-title: 2017 IEEE symposium on visualization for cyber security (VizSec)
  year: 2017
  ident: e_1_2_10_37_2
– ident: e_1_2_10_27_2
  doi: 10.1109/VAST.2018.8802509
– ident: e_1_2_10_25_2
  doi: 10.1609/aaai.v34i09.7079
– start-page: 3519
  volume-title: International Conference on Machine Learning
  year: 2019
  ident: e_1_2_10_22_2
– ident: e_1_2_10_41_2
  doi: 10.1109/TVCG.2016.2598838
– ident: e_1_2_10_24_2
  doi: 10.1109/TPAMI.2017.2773081
– ident: e_1_2_10_16_2
  doi: 10.1145/3027063.3053103
– start-page: 3987
  volume-title: International Conference on Machine Learning
  year: 2017
  ident: e_1_2_10_55_2
– ident: e_1_2_10_6_2
– ident: e_1_2_10_42_2
  doi: 10.1007/978-1-4615-5529-2_11
– ident: e_1_2_10_7_2
  doi: 10.1007/978-3-030-01252-6_33
– ident: e_1_2_10_14_2
– ident: e_1_2_10_20_2
  doi: 10.1609/aaai.v32i1.11595
– ident: e_1_2_10_53_2
– ident: e_1_2_10_49_2
  doi: 10.1109/TVCG.2022.3209347
– ident: e_1_2_10_45_2
– volume: 86
  start-page: 496
  year: 1986
  ident: e_1_2_10_44_2
  article-title: A case study of incremental concept induction
  publication-title: AAAI
– volume: 31
  year: 2018
  ident: e_1_2_10_30_2
  article-title: Visualizing the loss landscape of neural nets
  publication-title: Advances in neural information processing systems
– ident: e_1_2_10_13_2
– ident: e_1_2_10_31_2
  doi: 10.3389/fpsyg.2013.00504
– volume: 44
  start-page: 3366
  issue: 7
  year: 2021
  ident: e_1_2_10_12_2
  article-title: A continual learning survey: Defying forgetting in classification tasks
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– ident: e_1_2_10_3_2
  doi: 10.1109/ICCV.2019.00653
– ident: e_1_2_10_4_2
  doi: 10.1016/S0764-4469(97)82472-9
– ident: e_1_2_10_21_2
– ident: e_1_2_10_46_2
– ident: e_1_2_10_15_2
  doi: 10.1109/ICCV.2017.322
– start-page: 15699
  volume-title: International Conference on Machine Learning
  year: 2022
  ident: e_1_2_10_32_2
– ident: e_1_2_10_43_2
– ident: e_1_2_10_51_2
– ident: e_1_2_10_8_2
– ident: e_1_2_10_29_2
  doi: 10.1109/TVCG.2020.3030461
– ident: e_1_2_10_50_2
  doi: 10.1109/TVCG.2018.2864504
SSID ssj0004765
Score 2.4051154
Snippet Task‐incremental learning (Task‐IL) aims to enable an intelligent agent to continuously accumulate knowledge from new learning tasks without catastrophically...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 437
SubjectTerms Algorithms
CCS Concepts
Cognitive tasks
Computing methodologies → Visual analytics
Intelligent agents
Learning
Machine learning
Mathematical analysis
Neural networks
Theory of computation → Continual learning
Title Visual Analytics on Network Forgetting for Task‐Incremental Learning
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.14842
https://www.proquest.com/docview/2829802088
Volume 42
WOSCitedRecordID wos001020716600036&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library - Journals
  customDbUrl:
  eissn: 1467-8659
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004765
  issn: 0167-7055
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NSsNAEB5q60EP_ovVWoJ48BJosptkgyepRg-lFGmlt5Dd7paipNK0nn0En9EncWeTtBUUBG85zCZhZ2fnm92ZbwAuDWm5CohNKJbkhIGymXKJ7Qrtq7W7dBQ3mu4E3S4bDsNeBa7LWpicH2J54IaWYfZrNPCEZ2tGLsZKmzmjev-tYVGVjrxqt4_RoLMqiwx8r6T2RtKYglgIE3mWg7-7oxXGXEeqxtVEu__6yT3YKRCmdZMviX2oyPQAttd4Bw8heppkC5RBRhLkabamqdXNE8KtyBySYza0pQGt1U-y58_3D72P5CeJeljByTo-gkF0128_2EVDBVsQDDp9hwsNXxzRUh4RGhoRJrXLVjQkXANF5hKp4VyYUGz64vvC1woMVMjFyJfEF5QcQzWdpvIErEDHcYlMWoQzSql0mRJiNOKODDzuUcHqcFXOaywKtnFsevESl1GHnprYTE0dLpairznFxk9CjVI5cWFlWYy3wAy7jOLnjBp-f0Hcvo_Mw-nfRc9gC7vL55lhDajOZwt5DpvibT7JZk3YcGmvWSy6L6IO1wM
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NSsNAEB5KFdSD_2K1ahAPXgJtdpNswIsUY8VaeqjSW2i2u6UoqTStZx_BZ_RJnNkkbQUFwVsOs0nY2dn5dnbmG4ALQ1qufWYzTiU5ga9toR1mOxJ9NbrLuo6Nplt-uy16vaBTgquiFibjh5gH3MgyzH5NBk4B6SUrl0ONdi44bsArHL0SJfQ5vLOoivQ9t2D2Js6YnFeI8njmQ797owXEXAaqxtOEW__7x23YzBGmdZ0tiR0oqWQXNpZ4B_cgfBqlM5IhRhLiabbGidXOEsKt0ATJKRvaQkBrdfvp8-f7B-4jWSQRh-WcrMN9eAxvuo2mnTdUsCWjQ6dXjyXCl7qsaZdJhEZMKHTZmgcsRqAoHKYQzgV9Tk1fPE96qEBfB7EceIp5krMDKCfjRB2C5eM5rq_6NRYLzrlyhJZyMIjryndjl0tRgctiYiOZs41T04uXqDh14NREZmoqcD4Xfc0oNn4SqhbaiXIrSyO6BRbUZZQ-Z_Tw-wuixm1oHo7-LnoGa83uQytq3bXvj2GdOs1nWWJVKE8nM3UCq_JtOkonp2blfQF72diB
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NSsNAEB5KFdGD_2K1ahAPXgJNdpNswItUo2IJPVTpLSSb3VKUtDStZx_BZ_RJ3NkkbQUFwVsOs0nY2dn5Znb2G4ALTVouPWISildyfE-aTNrEtLny1cpdWjLRmu54Ycj6fb9bg6vqLkzBDzFPuKFl6P0aDVyMU7lk5XwglZ0zqjbgFep42ixt2l3civRcp2L2Rs6YklcI63jmQ797owXEXAaq2tMEW__7x23YLBGmcV0siR2oiWwXNpZ4B_cgeB7mM5RBRhLkaTZGmREWBeFGoJPkWA1tKEBr9OL85fP9Q-0jRSZRDSs5WQf78BTc9tr3ZtlQweQEg07XSriCLxZvSYdwBY0IE8plS-qTRAFFZhOh4JwfU2z64rrcVQr0pJ_w1BXE5ZQcQD0bZeIQDE_FcbGIWyRhlFJhM8l5miaW8JzEoZw14LKa2IiXbOPY9OI1qqIONTWRnpoGnM9FxwXFxk9CzUo7UWlleYSnwAy7jOLntB5-f0HUvgv0w9HfRc9grXsTRJ2H8PEY1rHRfFEk1oT6dDITJ7DK36bDfHKqF94XP7LX_A
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Visual+Analytics+on+Network+Forgetting+for+Task%E2%80%90Incremental+Learning&rft.jtitle=Computer+graphics+forum&rft.au=Li%2C+Ziwei&rft.au=Xu%2C+Jiayi&rft.au=Chao%2C+Wei%E2%80%90Lun&rft.au=Shen%2C+Han%E2%80%90Wei&rft.date=2023-06-01&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=42&rft.issue=3&rft.spage=437&rft.epage=448&rft_id=info:doi/10.1111%2Fcgf.14842&rft.externalDBID=n%2Fa&rft.externalDocID=10_1111_cgf_14842
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon